summaryrefslogtreecommitdiff
path: root/arch/arm64/crypto/sha2-ce-core.S
blob: 3f9d0f32698757893bd0440fca0ca5ee12e0c72e (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
/* SPDX-License-Identifier: GPL-2.0-only */
/*
 * sha2-ce-core.S - core SHA-224/SHA-256 transform using v8 Crypto Extensions
 *
 * Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
 */

#include <linux/linkage.h>
#include <asm/assembler.h>

	.text
	.arch		armv8-a+crypto

	dga		.req	q20
	dgav		.req	v20
	dgb		.req	q21
	dgbv		.req	v21

	t0		.req	v22
	t1		.req	v23

	dg0q		.req	q24
	dg0v		.req	v24
	dg1q		.req	q25
	dg1v		.req	v25
	dg2q		.req	q26
	dg2v		.req	v26

	.macro		add_only, ev, rc, s0
	mov		dg2v.16b, dg0v.16b
	.ifeq		\ev
	add		t1.4s, v\s0\().4s, \rc\().4s
	sha256h		dg0q, dg1q, t0.4s
	sha256h2	dg1q, dg2q, t0.4s
	.else
	.ifnb		\s0
	add		t0.4s, v\s0\().4s, \rc\().4s
	.endif
	sha256h		dg0q, dg1q, t1.4s
	sha256h2	dg1q, dg2q, t1.4s
	.endif
	.endm

	.macro		add_update, ev, rc, s0, s1, s2, s3
	sha256su0	v\s0\().4s, v\s1\().4s
	add_only	\ev, \rc, \s1
	sha256su1	v\s0\().4s, v\s2\().4s, v\s3\().4s
	.endm

	/*
	 * The SHA-256 round constants
	 */
	.section	".rodata", "a"
	.align		4
.Lsha2_rcon:
	.word		0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5
	.word		0x3956c25b, 0x59f111f1, 0x923f82a4, 0xab1c5ed5
	.word		0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3
	.word		0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174
	.word		0xe49b69c1, 0xefbe4786, 0x0fc19dc6, 0x240ca1cc
	.word		0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da
	.word		0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7
	.word		0xc6e00bf3, 0xd5a79147, 0x06ca6351, 0x14292967
	.word		0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13
	.word		0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85
	.word		0xa2bfe8a1, 0xa81a664b, 0xc24b8b70, 0xc76c51a3
	.word		0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070
	.word		0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5
	.word		0x391c0cb3, 0x4ed8aa4a, 0x5b9cca4f, 0x682e6ff3
	.word		0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208
	.word		0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2

	/*
	 * void sha2_ce_transform(struct sha256_ce_state *sst, u8 const *src,
	 *			  int blocks)
	 */
	.text
SYM_FUNC_START(sha2_ce_transform)
	frame_push	3

	mov		x19, x0
	mov		x20, x1
	mov		x21, x2

	/* load round constants */
0:	adr_l		x8, .Lsha2_rcon
	ld1		{ v0.4s- v3.4s}, [x8], #64
	ld1		{ v4.4s- v7.4s}, [x8], #64
	ld1		{ v8.4s-v11.4s}, [x8], #64
	ld1		{v12.4s-v15.4s}, [x8]

	/* load state */
	ld1		{dgav.4s, dgbv.4s}, [x19]

	/* load sha256_ce_state::finalize */
	ldr_l		w4, sha256_ce_offsetof_finalize, x4
	ldr		w4, [x19, x4]

	/* load input */
1:	ld1		{v16.4s-v19.4s}, [x20], #64
	sub		w21, w21, #1

CPU_LE(	rev32		v16.16b, v16.16b	)
CPU_LE(	rev32		v17.16b, v17.16b	)
CPU_LE(	rev32		v18.16b, v18.16b	)
CPU_LE(	rev32		v19.16b, v19.16b	)

2:	add		t0.4s, v16.4s, v0.4s
	mov		dg0v.16b, dgav.16b
	mov		dg1v.16b, dgbv.16b

	add_update	0,  v1, 16, 17, 18, 19
	add_update	1,  v2, 17, 18, 19, 16
	add_update	0,  v3, 18, 19, 16, 17
	add_update	1,  v4, 19, 16, 17, 18

	add_update	0,  v5, 16, 17, 18, 19
	add_update	1,  v6, 17, 18, 19, 16
	add_update	0,  v7, 18, 19, 16, 17
	add_update	1,  v8, 19, 16, 17, 18

	add_update	0,  v9, 16, 17, 18, 19
	add_update	1, v10, 17, 18, 19, 16
	add_update	0, v11, 18, 19, 16, 17
	add_update	1, v12, 19, 16, 17, 18

	add_only	0, v13, 17
	add_only	1, v14, 18
	add_only	0, v15, 19
	add_only	1

	/* update state */
	add		dgav.4s, dgav.4s, dg0v.4s
	add		dgbv.4s, dgbv.4s, dg1v.4s

	/* handled all input blocks? */
	cbz		w21, 3f

	if_will_cond_yield_neon
	st1		{dgav.4s, dgbv.4s}, [x19]
	do_cond_yield_neon
	b		0b
	endif_yield_neon

	b		1b

	/*
	 * Final block: add padding and total bit count.
	 * Skip if the input size was not a round multiple of the block size,
	 * the padding is handled by the C code in that case.
	 */
3:	cbz		x4, 4f
	ldr_l		w4, sha256_ce_offsetof_count, x4
	ldr		x4, [x19, x4]
	movi		v17.2d, #0
	mov		x8, #0x80000000
	movi		v18.2d, #0
	ror		x7, x4, #29		// ror(lsl(x4, 3), 32)
	fmov		d16, x8
	mov		x4, #0
	mov		v19.d[0], xzr
	mov		v19.d[1], x7
	b		2b

	/* store new state */
4:	st1		{dgav.4s, dgbv.4s}, [x19]
	frame_pop
	ret
SYM_FUNC_END(sha2_ce_transform)